Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    compatibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sonraki
    -0.07
    	Task
    -0.06
     Δι
    -0.06
    thumb
    -0.06
     разд
    -0.06
     wcs
    -0.06
    Journal
    -0.06
     entr
    -0.06
     flour
    -0.06
     Presenter
    -0.06
    POSITIVE LOGITS
    029
    0.07
     buoy
    0.07
     �
    0.06
     elit
    0.06
     трохи
    0.06
     faithfully
    0.06
     gente
    0.06
    価
    0.06
    译
    0.06
    rgctx
    0.06
    Act Density 0.008%

    No Known Activations